文献类型：期刊文献

英文题名：Study on an improved bee colony algorithm and its application in optimization of PX oxidation process

作者：Li, Xinmao[1]; Xing, Jianliang[2]; Luo, Na[1]; Zhong, Weimin[1]; Cheng, Hui[1]; Qian, Feng[1]

机构：[1] Key Laboratory of Advanced Control and Optimization for Chemical Processes, East China University of Science and Technology, Shanghai, China; [2] College of Chemical Engineering, East China University of Science and Technology, Shanghai, China

年份：2011

起止页码：6P

外文期刊名：IWACIII 2011 - International Workshop on Advanced Computational Intelligence and Intelligent Informatics, Proceedings

收录：EI(收录号：20130916070689)

语种：英文

外文关键词：Oxidation - Evolutionary algorithms - Xylene

摘要：For the deficiencies of the basic bee colony algorithm based on the mechanism of nectar (ABC), such as the population diversity scarcity in the early iterations and easily sticking into the local optimum, a strategy which integrates an improved differential evolution (DE) method into bee colony algorithm (DE-ABC) is proposed. The primary idea of DE-ABC is to introduce DE into the mutation of employed bee instead of random search strategy, and combination of incremental strategy of the crossover probability factor and the scaling factor, strategy of stagnation judgment and treatment. Four benchmark functions are used to make a comparison, and results show that DE-ABC converges with a faster accelerated rate and a higher accuracy optimization. Then DE-ABC is applied to the optimization of p-xylene oxidation process. With the purpose of reducing the exhaust CO, CO2 of the reactor and the first crystallizer, an excellent solution of the operating variables is obtained under the process operating parameters constraints, which gives a guide to the plant operation.